fix(cohere): support max_completion_tokens on cohere v2 chat (default route)

litellm/llms/cohere/chat/v2_transformation.py

@@ -120,6 +120,7 @@ def get_supported_openai_params(self, model: str) -> List[str]:
             "stream",
             "temperature",
             "max_tokens",
+            "max_completion_tokens",
             "top_p",
             "frequency_penalty",
             "presence_penalty",
@@ -143,7 +144,12 @@ def map_openai_params(
                 optional_params["stream"] = value
             if param == "temperature":
                 optional_params["temperature"] = value
-            if param == "max_tokens":
+            if (
+                param == "max_tokens"
+                and "max_completion_tokens" not in non_default_params
+            ):
+                optional_params["max_tokens"] = value
+            if param == "max_completion_tokens":
                 optional_params["max_tokens"] = value
             if param == "n":
                 optional_params["num_generations"] = value

tests/test_litellm/llms/cohere/chat/test_cohere_transformation.py

@@ -6,7 +6,9 @@
     0, os.path.abspath("../../../../..")
 )  # Adds the parent directory to the system path
 
+import litellm
 from litellm.llms.cohere.chat.transformation import CohereChatConfig
+from litellm.llms.cohere.chat.v2_transformation import CohereV2ChatConfig
 
 
 class TestCohereTransform:
@@ -49,3 +51,69 @@ def test_cohere_max_tokens_backward_compat(self):
 
         # The function should properly map max_tokens if max_completion_tokens is not provided
         assert result == {"temperature": 0.7, "max_tokens": 200}
+
+
+class TestCohereV2Transform:
+    def setup_method(self):
+        self.config = CohereV2ChatConfig()
+        self.model = "command-r"
+
+    def test_v2_supports_max_completion_tokens(self):
+        """max_completion_tokens must be advertised so get_optional_params does not reject it"""
+        assert "max_completion_tokens" in self.config.get_supported_openai_params(
+            self.model
+        )
+
+    def test_v2_max_tokens_only_still_maps(self):
+        """max_tokens alone maps to cohere max_tokens when max_completion_tokens is absent"""
+        result = self.config.map_openai_params(
+            non_default_params={"temperature": 0.7, "max_tokens": 200},
+            optional_params={},
+            model=self.model,
+            drop_params=False,
+        )
+
+        assert result == {"temperature": 0.7, "max_tokens": 200}
+
+    def test_v2_map_max_completion_tokens_overrides_max_tokens(self):
+        """max_completion_tokens maps to cohere max_tokens and overrides max_tokens, matching v1"""
+        result = self.config.map_openai_params(
+            non_default_params={
+                "temperature": 0.7,
+                "max_tokens": 200,
+                "max_completion_tokens": 256,
+            },
+            optional_params={},
+            model=self.model,
+            drop_params=False,
+        )
+
+        assert result == {"temperature": 0.7, "max_tokens": 256}
+
+    def test_v2_max_completion_tokens_precedence_is_order_independent(self):
+        """max_completion_tokens wins over max_tokens regardless of dict ordering"""
+        max_tokens_first = self.config.map_openai_params(
+            non_default_params={"max_tokens": 200, "max_completion_tokens": 256},
+            optional_params={},
+            model=self.model,
+            drop_params=False,
+        )
+        max_completion_first = self.config.map_openai_params(
+            non_default_params={"max_completion_tokens": 256, "max_tokens": 200},
+            optional_params={},
+            model=self.model,
+            drop_params=False,
+        )
+
+        assert max_tokens_first == {"max_tokens": 256}
+        assert max_completion_first == {"max_tokens": 256}
+
+    def test_v2_default_route_accepts_max_completion_tokens(self):
+        """The default cohere_chat route resolves to v2; max_completion_tokens must not raise"""
+        optional_params = litellm.get_optional_params(
+            model=self.model,
+            custom_llm_provider="cohere_chat",
+            max_completion_tokens=256,
+        )
+
+        assert optional_params["max_tokens"] == 256